中科院分詞系統NLPIR的JAVA代碼（批量讀取文件）

準備工作：

• 最新NLPIR分詞系統下載包http://ictclas.nlpir.org/downloads
• 授權文件更新：https://github.com/NLPIR-team/NLPIR/tree/431b6351f30ed7d606ac50fde1f4456c596998df/License或者https://github.com/NLPIR-team/NLPIR/tree/master/License
  在eclipse中導入中科院分詞系統下載包中sample->JnaTest_NLPIR項目，優化NlpirTest.java文件代碼。
  其中，官方原始demo代碼需要更改的地方：

CLibrary Instance = (CLibrary) Native.loadLibrary(
                "D:\\tools\\NLPIR\\lib\\win64\\NLPIR", CLibrary.class);

中路徑改爲自己操作系統的.dll和.lib的上一級目錄，並加上NLPIR，不要後綴名

public static void main(String[] args) throws Exception {
String argu = "D:\\tools\\NLPIR";

路徑改爲Data文件夾的上一級目錄

☆注：遇到初始化問題，如果是文件過期問題，在上面鏈接中下載對應的最新授權文件,並替換掉項目裏Data文件下對應的授權文件；如果是配置問題，可能是導入的項目路徑中有中文。

本代碼可實現功能：

1. 普通批量分詞
2. 添加用戶詞典txt後批量
3. 批量提取關鍵字

package code;

import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.PrintWriter;
import java.io.UnsupportedEncodingException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;

import com.sun.jna.Library;
import com.sun.jna.Native;

public class Nlpir {

    // 定義接口CLibrary，繼承自com.sun.jna.Library
    public interface CLibrary extends Library {
        // 定義並初始化接口的靜態變量
        CLibrary Instance = (CLibrary) Native.loadLibrary(
                "D:\\tools\\NLPIR\\lib\\win64\\NLPIR", CLibrary.class);

        public int NLPIR_Init(String sDataPath, int encoding,
                String sLicenceCode);               
        public String NLPIR_ParagraphProcess(String sSrc, int bPOSTagged); //對字符串內容進行分詞
        public String NLPIR_GetKeyWords(String sLine, int nMaxKeyLimit,
                boolean bWeightOut); //從字符串中提取關鍵詞
        public String NLPIR_GetFileKeyWords(String sLine, int nMaxKeyLimit,
                boolean bWeightOut); //從txt文件中提取關鍵詞，本代碼未用到
        public int NLPIR_AddUserWord(String sWord);
        public String NLPIR_GetLastErrorMsg();
        public void NLPIR_Exit();
    }

    public static String transString(String aidString, String ori_encoding,
            String new_encoding) {
        try {
            return new String(aidString.getBytes(ori_encoding), new_encoding);
        } catch (UnsupportedEncodingException e) {
            e.printStackTrace();
        }
        return null;
    }

    public static void main(String[] args) throws Exception {
        String argu = "D:\\tools\\NLPIR"; //Data的上一級目錄
        String system_charset = "UTF-8";
        int charset_type = 1;       
        int init_flag = CLibrary.Instance.NLPIR_Init(argu, charset_type, "0");
        String nativeBytes = null;
        if (0 == init_flag) {
            nativeBytes = CLibrary.Instance.NLPIR_GetLastErrorMsg();
            System.err.println("初始化失敗！fail reason is "+nativeBytes);
            return;
        }
        /*添加用戶詞典功能*/
        String userFilePath = "D:\\tools\\userdic.txt";
        File userFile = new File(userFilePath);
        InputStreamReader readerUser = new InputStreamReader(new FileInputStream(userFile), "gbk");
        BufferedReader brUser = new BufferedReader(readerUser);
        String lineUser="";
        List<String> list = new ArrayList<String>();
        while((lineUser = brUser.readLine()) != null){
            String[] strings = lineUser.split("\n");
            for(int i = 0; i < strings.length; i++){
                list.add(strings[i]);
            }
        }
        brUser.close();

        /*實現批量讀取多個要分詞的TXT文件*/
        String sInput = "";
        String path = "D:\\tools\\source";
        String outName = "";
        File file = new File(path);
        File[] files = file.listFiles();
        String out = "";
        Arrays.sort(files);
        for(int i = 0; i < files.length; i++){
            if (files[i].isFile()){
                out = "";
                outName = files[i].getName();
                InputStreamReader reader = new InputStreamReader(new FileInputStream(files[i]), "gbk");
                BufferedReader br = new BufferedReader(reader);
                String line="";
                sInput = "";
                line = br.readLine();
                while (line != null){
                    sInput += line;
                    line = br.readLine();
                }
                br.close();

            try {
                nativeBytes = CLibrary.Instance.NLPIR_ParagraphProcess(sInput, 1);
                out += "未添加用戶詞典的分詞結果是： "; //對應TXT的內容
                out += nativeBytes;
                out += "\r\n";

                for(int k = 0; k < list.size(); k++){
                    CLibrary.Instance.NLPIR_AddUserWord(list.get(k)); //用戶詞典txt中的詞用空格隔開
                }
                /*屏蔽這三行OR上段未添加用戶詞典的分詞結果，使result結果中只出現一種結果，否則兩者都出現在TXT中
                out += "增加用戶詞典後分詞結果是： "; //對應TXT的內容
                out += nativeBytes;
                out += "\r\n";
                */              

                int nCountKey = 0;
                String nativeByte = CLibrary.Instance.NLPIR_GetKeyWords(sInput, 10,false);
                File fp1 = new File("D:\\tools\\keyword\\" + outName);
                PrintWriter pfp1 = new PrintWriter(fp1);
                pfp1.write("關鍵詞爲：" + nativeByte); //對應TXT內容
                pfp1.close();

                //分詞結果(添加和未添加用戶詞典的分詞結果)
                File fp = new File("D:\\tools\\result\\" + outName);
                PrintWriter pfp = new PrintWriter(fp);
                pfp.write(out);
                pfp.close();

            } catch (Exception ex) {
                // TODO Auto-generated catch block
                ex.printStackTrace();
            }
            }
        }
        CLibrary.Instance.NLPIR_Exit();

    }
}

還有需要完善的地方，希望多多交流！！！